INDEX

Explanations

references to historical events, specifically the Boston Massacre

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inas

-0.15

omic

-0.14

æ¢

-0.14

è¨Ĭ

-0.13

Cop

-0.13

oon

-0.13

vib

-0.13

anky

-0.13

oad

-0.13

oret

-0.13

POSITIVE LOGITS

allest

0.18

olley

0.16

 Lindsey

0.14

TestFixture

0.14

ackers

0.13

andex

0.13

esz

0.13

áº¡ng

0.13

itle

0.13

Activations Density 0.000%

references to historical events, specifically the Boston Massacre

No Comments

No Known Activations